The building sector is responsible for excessive amounts of energy consumption and energy related emissions. The need to implement sustainable technology is crucial, such as heat pumps. However, faults within the system puts a strain on energy consumption. Studies have revealed that digital monitoring has the possibility to enhance energy-efficiency. Specifically, Machine Learning techniques has proven to be successful in the field of system optimization and fault detection which can help reduce energy consumption and additional costs. The aim of this thesis is to investigate how data analysis and Machine Learning techniques can be used to make performance predictions of heat pump systems.This thesis focuses on developing regression models for heat pump performance predictions using data from real-time field measurements from two ground-source heat pumps connected to a large facility. The predicted performance metrics are the Coefficient of Performance (COP) and Carnot efficiency. The research methodology includes a literature review, data pre-processing, feature selection and model development. The data was pre-processed to remove unsatisfactory information, and relevant input features were identified during feature selection. Regression models were developed ranging from simple linear to non-linear regression with up to four input features and third-degree polynomial. The models were evaluated using three different model evaluation metrics.The results of this thesis revealed that the best performing models for predicting COP were non-linear, including three to four input features with a third-degree polynomial. These models were able to achieve over 90% accuracy. However, models predicting Carnot efficiency showed deviations for one of the heat pumps. These results revealed the importance of the feature selection process when developing regression models. The significant features to consider were revealed to be the discharge refrigerant (the temperature of the refrigerant at compressor outlet) and the compressor voltage signal. The data analysis process and regression models revealed assumed measurement error or faults in one of the heat pump systems.In conclusion, this study emphasizes the effectiveness of Machine Learning techniques for heat pump performance predictions, specifically highlighting the role of feature selection.

A ratchet is an asymmetric, non-equilibrated system that can produce a directed current of particles without the need for macroscopic potential gradients. In rocked quantum electron ratchets, tunnelling and wave-reflection can induce reversals in the direction of the net current as a function of system parameters. An asymmetric quantum point contact in a GaAs/GaAlAs heterostructure has been studied experimentally as a realisation of a quantum electron ratchet. A Landauer model predicts reversals in the direction of the net current as a function of temperature, amplitude of the rocking voltage, and Fermi energy. Artifacts such as circuit-induced asymmetry, also known as self-gating, were carefully removed from the experimental data, which showed net current and net differential conductance reversals, as predicted by the model. The model also predicts the existence of a heat current where the net electron current changes sign, as equal numbers of high and low energy electrons are pumped in opposite directions. An idealised quantum electron ratchet is studied analytically as an energy selective electron heat engine and refrigerator. The hypothetical device considered consists of two electron reservoirs with different temperatures and Fermi energies. The reservoirs are linked via a resonant state in a quantum dot, which functions as an idealised energy filter for electrons. The efficiency of the device approaches the Carnot value when the energy transmitted by the filter is tuned to that where the Fermi distributions in the reservoirs are equal. The maximum power regime, where the filter transmits all electrons that contribute positively to the power, is also examined. Analytic expressions are obtained for the power and efficiency of the idealised device as both a heat engine and as a refrigerator in this regime of operation. The expressions depend on the ratio of the voltage to the difference in temperature of the reservoirs, and on the ratio of the reservoir temperatures. The energy selective electron heat engine is shown to be non-endoreversible, and to operate in an analogous manner to the three-level amplifier, a laser based quantum heat engine. Implications for improving the efficiency of thermionic refrigerators and power generators are discussed.